Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83f3f1f4307caacd0a1dce95711b6bba3e99031401d367bf00ed14a9b1bc8f21
+oid sha256:789099940226720248f39fd98f1354804b01bff8bec9ff29fc391ae722d2f9a2
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76773048a5b5d17c02ca4f3a581618f2ea1655aaa681494f59c527ed85285e7
+oid sha256:8145422420c5ce86bf2fdfd9352db5954b909452458a3fc771fc0026b82bd534
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62102b3298905fdfc47722adc9b328add3ef83064b8d374b7ad380c660eb92fd
+oid sha256:11c009937b60a292171e281a94f457805129e19bc2dea5d1a961a096ff756ce0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8389763832092285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.005296259516716319,
+  "best_metric": 1.824175477027893,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.007944389275074478,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.281,
       "eval_steps_per_second": 7.64,
       "step": 20
+    },
+    {
+      "epoch": 0.005561072492552135,
+      "grad_norm": 0.7575086951255798,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4433,
+      "step": 21
+    },
+    {
+      "epoch": 0.006355511420059583,
+      "grad_norm": 0.9018149375915527,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.0698,
+      "step": 24
+    },
+    {
+      "epoch": 0.006620324395895399,
+      "eval_loss": 1.8268407583236694,
+      "eval_runtime": 104.0805,
+      "eval_samples_per_second": 15.277,
+      "eval_steps_per_second": 7.638,
+      "step": 25
+    },
+    {
+      "epoch": 0.007149950347567031,
+      "grad_norm": 1.0376005172729492,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8279,
+      "step": 27
+    },
+    {
+      "epoch": 0.007944389275074478,
+      "grad_norm": 0.7100544571876526,
+      "learning_rate": 0.0,
+      "loss": 1.5161,
+      "step": 30
+    },
+    {
+      "epoch": 0.007944389275074478,
+      "eval_loss": 1.824175477027893,
+      "eval_runtime": 105.2797,
+      "eval_samples_per_second": 15.103,
+      "eval_steps_per_second": 7.551,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2484032747077632.0,
+  "total_flos": 3639968777895936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null